wan-2.5-preview/text-to-image

POST

/openapi/v2/alibaba/wan-2.5-preview/text-to-image

Wan 2.5 Preview Text-to-Image is AI image generation model from Alibaba Tongyi Wanxiang series. It creates high-quality images from text descriptions with 5 standard aspect ratios, batch generation up to 4 images, intelligent prompt extension and negative prompt support, ideal for creative design and content creation.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "Golden hour window-side portrait nine-grid, the same young adult (default male) maintaining completely consistent facial features, skin tone, eye shape, and natural expression. Long straight light brown hair naturally draped over shoulders, wearing a simple dark-colored logo-free T-shirt. Nine poses include: looking up to the light, smiling facing forward, side profile with lowered gaze, glancing back, relaxed lip close-up, hand running through hair, leaning back toward light, clean side profile, hand supporting chin in contemplation. Unified warm-toned window light casting soft shadows, natural skin texture with gentle highlights, sharply focused face with blurred background. 3×3 grid layout, minimalist indoor atmosphere, Instagram-style edited portrait aesthetics, overall calm, intimate, and beautiful.",
    "size": "1280*1280",
    "n": 1,
    "promptExtend": true
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://www.runninghub.ai/openapi/v2/alibaba/wan-2.5-preview/text-to-image' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "Golden hour window-side portrait nine-grid, the same young adult (default male) maintaining completely consistent facial features, skin tone, eye shape, and natural expression. Long straight light brown hair naturally draped over shoulders, wearing a simple dark-colored logo-free T-shirt. Nine poses include: looking up to the light, smiling facing forward, side profile with lowered gaze, glancing back, relaxed lip close-up, hand running through hair, leaning back toward light, clean side profile, hand supporting chin in contemplation. Unified warm-toned window light casting soft shadows, natural skin texture with gentle highlights, sharply focused face with blurred background. 3×3 grid layout, minimalist indoor atmosphere, Instagram-style edited portrait aesthetics, overall calm, intimate, and beautiful.",
    "size": "1280*1280",
    "n": 1,
    "promptExtend": true
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Body

Examples

Submit response exampleTask success response example

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

Modified at 2026-04-23 12:00:02

f-dev

wan-2.7/text-to-image-pro